Triple
T4225280
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lev Kamenev |
E94441
|
entity |
| Predicate | relationType |
P10690
|
FINISHED |
| Object | brother‑in‑law of Leon Trotsky |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: brother‑in‑law of Leon Trotsky | Statement: [Lev Kamenev, relationType, brother‑in‑law of Leon Trotsky]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationType Context triple: [Lev Kamenev, relationType, brother‑in‑law of Leon Trotsky]
-
A.
relationshipType
chosen
Indicates the specific kind of relationship that exists between two or more entities.
-
B.
relatedType
Indicates that one entity is connected to another through a specified type or category of relationship.
-
C.
termRelationTo
Indicates a general relational association between one term and another, without specifying the exact nature of that relationship.
-
D.
semanticRelation
Indicates a general meaning-based connection between two entities, such as similarity, implication, or conceptual association.
-
E.
valueRelation
Indicates a comparative or associative relationship between the values or magnitudes of two or more entities.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69b3453700a08190ae88792e3dc63207 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34e4d32d481909df7b18f502945b8 |
completed | March 12, 2026, 11:37 p.m. |
| PD | Predicate disambiguation | batch_69b347f1d7b48190bd8974c03c7dc937 |
completed | March 12, 2026, 11:10 p.m. |
Created at: March 12, 2026, 11:04 p.m.